plugins/rephrase/skills/humanize/SKILL.md
Rewrite a piece of text that reads as machine-generated so it sounds like a person wrote it — strip the telltale AI tics (throat-clearing openers, inflated diction, rule-of-three padding, em-dash drama, tacked-on participial clauses) while keeping every point intact. Use when the user explicitly asks to humanize, de-AI, make text sound human, or remove the AI / ChatGPT / Claude voice from a passage, document, or draft they point to, including text just produced in the conversation. Do not trigger as unprompted cleanup of text the user has not asked to change; when the problem is length rather than voice use the tighten or distil skill, and when the problem is specialist jargon rather than machine cadence use the plain skill.
npx skillsauth add shihyuho/skills humanizeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Re-examine a passage that reads as machine-generated and rewrite it so it reads like a person wrote it. The points stay; the AI cadence goes. Humanizing is lossless on content — it changes voice, not substance.
The user identifies the target — pasted text, a file path, or a passage in this conversation. If they invoke the skill without naming one, humanize the last substantial passage you wrote; needing your own output de-AI'd is the usual reason this skill is used. Ask only if the target is genuinely ambiguous.
You cannot humanize by find-and-replacing tics one at a time. Swapping "utilize" for "use" leaves the underlying cadence — the relentless symmetry, the throat-clearing, the wind-down clauses — fully intact, and the text still reads as machine-made. Do not patch. Work out what the passage actually says, then re-express it the way a person would say it out loud: uneven sentence lengths, plain verbs, one idea at a time, willing to start a sentence with And or But and to stop when the point lands.
These are what make prose read as AI-generated. Cut them on sight:
This list is a guide, not a checklist to satisfy. The goal is prose a person would actually write, not prose with these specific strings removed.
Give the rewritten text, then a short report of which kinds of tics were cut — so the reader can confirm the voice changed while the substance held.
development
Write a short author's briefing to hand to a code reviewer whose agent already has its own review skill, so it supplies the context that skill can't see instead of repeating how to review. Right after you finish a piece of work, it mines this session (and any kickoff implementation-notes) for what the reviewer most needs flagged — the easy-to-miss changes, the parts you're least sure about, the looks-wrong-but-intentional bits, and the blast radius — plus the exact commit range to review. Use when you've just finished work and want to hand the review off to another agent, chat, or teammate, when you want a "heads-up for the reviewer", or when packaging a change for review elsewhere. It does not perform the review and does not re-specify severity tiers or output format — that's the reviewer's own skill's job.
testing
Use when creating, rewriting, pruning, or reviewing `AGENTS.md` or `CLAUDE.md`, especially to remove repo summaries, stale rules, and other low-signal global instructions. Trigger when deciding what belongs in always-on agent files versus a task-specific skill.
development
Drive a structured tutoring workflow that turns Claude into a learning onramp accelerator — consultative diagnosis → custom syllabus → unit-by-unit guided lessons with notes/whiteboard → dynamic adjustment from an accumulating learner profile. Use when the user states a learning goal ("I want to systematically learn X", "teach me Y", "help me prep for Z exam"), uploads study materials and asks for a course plan, or signals sustained guided study (mentions tutor, syllabus, course, lessons, study plan, curriculum, 家教, 學習路徑). Skip for one-shot factual Q&A or quick code-context explanations.
tools
Produce a TL;DR of a given target. Use when the user asks for a tldr, tl;dr, or quick summary of anything.